Jurnal Teknologi Informasi dan Ilmu Komputer最新文献

{"title":"Sistem Kontrol Perangkat Inframerah Menggunakan Speech Recognition dengan Spectrogram dan Convolutional Neural Network Berbasis Mikrokontroler","authors":"Irfan Muzakky Nurrizqy, Barlian Henryranu Prasetio, Rekyan Regasari Mardi Putri","doi":"10.25126/jtiik.20231056909","DOIUrl":"https://doi.org/10.25126/jtiik.20231056909","url":null,"abstract":"Menurut data dari Biro Pusat Statistik (BPS), terdapat sebanyak 22,5 juta dari penduduk Indonesia merupakan penyandang disabilitas. Angka ini berjumlah sekitar lima persen dari keseluruhan penduduk Indonesia. Di zaman sekarang, kemajuan teknologi di seluruh dunia berkembang dengan pesat, sehingga muncul banyak hal yang dapat membantu menyederhanakan kehidupan semua orang, terutama penyandang disabilitas. Salah satu hal yang membantu penyandang disabilitas adalah munculnya perangkat pintar yang dapat dikendalikan menggunakan indra selain tangan, seperti suara. Penelitian ini bertujuan untuk mengembangkan sistem yang dapat mengendalikan perangkat inframerah dengan menggunakan suara sebagai input. Sistem tersebut akan dikembangkan menggunakan mikrokontroler dan metode speech recognition yang terdiri dari spectrogram dan CNN. Penelitian ini direncanakan untuk tujuan untuk membantu penyandang disabilitas dalam mengendalikan perangkat-perangkat di sekitar rumah. Hasil pengujian menunjukkan bahwa akurasi model CNN sebesar 93% dan akurasi percobaan terhadap pengguna sebesar 74,25%. Sistem ini juga dapat menjalankan proses speech recognition dengan waktu rata-rata 0,105 detik. Jarak optimal yang diperlukan antara pengguna dengan mikrofon adalah 30 cm dan jarak optimal yang diperlukan antara transmitter inframerah dengan perangkat yang dikendalikan adalah 30 cm. Abstract According to data from the Central Bureau of Statistics (BPS), around 22.5 million of Indonesia's population are people with disabilities. This number amounts to about five percent of Indonesia's total population. In the present day, where technology advances are rapidly developing all around the world, there have been many things that can help simplify the lives of everyone in the world, especially people with disabilities. One thing that helps people with disabilities is the emergence of smart devices that do not need to be controlled using hands but can use other senses such as sound. This research aims to develop a system that can control infrared devices using sound as input. The system will be developed using microcontrollers and speech recognition methods consisting of spectrogram and CNN. This research is conducted with the goal of helping people with disabilities in controlling devices around the house. Testing results show that the accuracy of the CNN model is 93% and the accuracy of trials on users is 74.25%. The system can also run the speech recognition process with an average time of 0.105 seconds. The optimal distance required between the user and microphone is 30 cm and the optimal distance required between the infrared transmitter and the controlled device is 30 cm.","PeriodicalId":32501,"journal":{"name":"Jurnal Teknologi Informasi dan Ilmu Komputer","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136077634","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Segmentasi Pelanggan B2B dengan Model LRFM Menggunakan Algoritma Fuzzy C-Means pada Rotte Bakery","authors":"Dea Putri Ananda, Siti Monalisa","doi":"10.25126/jtiik.20231056569","DOIUrl":"https://doi.org/10.25126/jtiik.20231056569","url":null,"abstract":"Pelanggan B2B (Business to Business) merupakan pelanggan yang membeli produk dari suatu perusahaan dengan tujuan menjualnya kembali kepada konsumen akhir. Oleh karena itu, pengelolaan pelanggan B2B dengan strategi yang baik dan tepat sangatlah penting. Setiap pelanggan memiliki karakteristik yang berbeda, termasuk perilaku pembelian, demografi, dan geografi. Oleh karena itu, segmentasi pelanggan perlu dilakukan untuk mengelompokkan pelanggan dengan karakteristik serupa. Dengan demikian, perusahaan dapat menerapkan strategi pemasaran yang lebih efektif dan sesuai dengan kebutuhan setiap segmen pelanggan. Dalam penelitian ini, kami menggunakan model LRFM (Length, Recency, Frequency, dan Monetary) dengan Algoritma Fuzzy C-Means untuk melakukan segmentasi pelanggan. Metode validasi Davies Bouldien-Index digunakan untuk menentukan jumlah cluster yang optimal. Hasilnya menunjukkan bahwa terdapat lima cluster yang optimal untuk pelanggan agen dengan nilai DBI sebesar 0,57, sedangkan pelanggan outlet memiliki empat cluster dengan nilai DBI sebesar 0,49. Karakteristik yang dihasilkan untuk pelanggan agen adalah Average Value Segment, New Low Value Customer, New Dormant Segment, Golden Segment, dan Superstar Segment. Sementara itu, pelanggan outlet terbagi menjadi Golden Segment, Superstar Segment, New Low Value Customer, dan Dormant Segment. Berdasarkan temuan tersebut, kami memberikan usulan strategi pemasaran yang sesuai dengan karakteristik masing-masing segmen pelanggan B2B. Usulan ini relevan baik bagi akademisi, praktisi, maupun peneliti dalam bidang pemasaran. Abstract B2B customers (Business to Business) are customers who purchase products from a company with the intention of reselling them to end consumers. Therefore, managing B2B customers with effective and appropriate strategies is crucial. Each customer has different characteristics, including purchasing behavior, demographics, and geography. Therefore, customer segmentation is necessary to group customers with similar characteristics. This enables companies to implement more effective and targeted marketing strategies tailored to the needs of each customer segment. In this study, we employed the LRFM model (Length, Recency, Frequency, and Monetary) with the Fuzzy C-Means algorithm for customer segmentation. The Davies Bouldien-Index validation method was used to determine the optimal number of clusters. The results revealed that there are five optimal clusters for agent customers with a DBI value of 0.57, while outlet customers have four clusters with a DBI value of 0.49. The resulting characteristics for agent customers are the Average Value Segment, New Low Value Customer, New Dormant Segment, Golden Segment, and Superstar Segment. Meanwhile, outlet customers are divided into the Golden Segment, Superstar Segment, New Low Value Customer, and Dormant Segment. Based on these findings, we propose marketing strategies that align with the characteristics of each B2B customer segment. These prop","PeriodicalId":32501,"journal":{"name":"Jurnal Teknologi Informasi dan Ilmu Komputer","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136078166","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Easy Data Augmentation untuk Data yang Imbalance pada Konsultasi Kesehatan Daring","authors":"Anisa Nur Azizah, Misbachul Falach Asy'ari, Ifnu Wisma Dwi Prastya, Diana Purwitasari","doi":"10.25126/jtiik.20231057082","DOIUrl":"https://doi.org/10.25126/jtiik.20231057082","url":null,"abstract":"Pendekatan augmentasi teks sering digunakan untuk menangani imbalance data pada kasus klasifikasi teks, seperti teks Konsultasi Kesehatan Daring (KKD), yaitu alodokter.com. Teknik oversampling dapat mengatasi kondisi skewed terhadap kelas mayoritas. Namun, augmentasi teks dapat mengubah konten dan konteks teks karena kata-kata teks tambahan yang berlebihan. Penelitian kami menyelidiki algoritma Easy Data Augmentation (EDA), yang berbasis parafrase kalimat dalam teks KKD dengan menggunakan teknik Synonym Replacement (SR), Random Insertion (RI), Random Swap (RS), dan Random Deletion (RD). Kami menggunakan Tesaurus Bahasa Indonesia untuk mengubah sinonim di EDA dan melakukan percobaan pada parameter yang dibutuhkan oleh algoritma untuk mendapatkan hasil augmentasi teks yang optimal. Kemudian, percobaan menyelidiki proses augmentasi kami menggunakan pengklasifikasi Random Forest, Naïve Bayes, dan metode berbasis peningkatan seperti XGBoost dan ADABoost, yang menghasilkan peningkatan akurasi rata-rata sebesar 0,63. Hasil parameter EDA terbaik diperoleh dengan menambahkan nilai 0,1 pada semua teknik EDA mendapatkan 88,86% dan 88,44% untuk akurasi dan nilai F1-score. Kami juga memverifikasi hasil EDA dengan mengukur koherensi teks sebelum dan sesudah augmentasi menggunakan pemodelan topik Latent Dirichlet Allocation (LDA) untuk memastikan konsistensi topik. Proses EDA dengan RI memberikan koherensi yang lebih baik sebesar 0,55 dan dapat mendukung implementasi EDA untuk menangani imbalance data, yang pada akhirnya dapat meningkatkan kinerja klasifikasi. Abstract The text augmentation approach is often utilized for handling imbalanced data of classifying text corpus, such as online health consultation (OHC) texts, i.e., alodokter.com. The oversampling technique can overcome the skewed condition towards majority classes. However, text augmentation could change text content and context because of excessive words of additional texts. Our work investigates the Easy Data Augmentation (EDA) algorithm, which is sentence paraphrase-based in the OHC texts that often in non-formal sentences by using techniques of synonym replacement (SR), random insertion (RI), random swap (RS), and random deletion (RD). We employ the Indonesian thesaurus for changing synonyms in the EDA and do empirical experiments on parameters required by the algorithm to obtain optimal results of text augmentation. Then, the experiments investigate our augmentation process using classifiers of Random Forest, Naïve Bayes, and boosting-based methods like XGBoost and ADABoost, which resulted in an average accuracy increase of 0.63. The best EDA parameter results were acquired by adding a value of 0.1 in all EDA techniques to get 88.86% and 88.44% for accuracy and F1-score values. We also verified the EDA results by measuring coherences of texts before and after augmentation using a topic modeling of Latent Dirichlet Allocation (LDA) to ensure topic consistency. The EDA process with RI gave better ","PeriodicalId":32501,"journal":{"name":"Jurnal Teknologi Informasi dan Ilmu Komputer","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136077627","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Pengembangan Sistem Monitoring Pendataan Aplikasi Berbasis Web pada Kementerian Pekerjaan Umum dan Perumahan Rakyat","authors":"Salma Nada Safira, Yusi Tyroni Mursityo, Mochamad Chandra Saputra","doi":"10.25126/jtiik.20231056891","DOIUrl":"https://doi.org/10.25126/jtiik.20231056891","url":null,"abstract":"Kementerian Pekerjaan Umum dan Perumahan Rakyat adalah kementerian Indonesia yang mempunyai tugas menyelenggarakan kegiatan pemerintahan di bidang pekerjaan umum dan perumahan rakyat untuk membantu Presiden. Perangkat lunak yang dimiliki oleh Kementerian PUPR sangat banyak, sehingga membutuhkan monitoring pendataan aplikasi. Pada pemantauan aplikasi di kementerian PUPR masih menggunakan Google Workspace, proses tersebut menyebabkan harus melakukan pengecekan setiap aplikasi dan menjadi tidak efisien. Sehingga, membutuhkan adanya solusi dengan pengembangan sistem monitoring aplikasi. Aktivitas pada sistem monitoring dengan melacak status aplikasi, dan melakukan pengelolaan data perangkat lunak. Metode Rational Unified Process (RUP) digunakan untuk membuat aplikasi. Pendekatan dilakukan menggunakan pengembangan berorientasi objek dengan UML. Proses implementasi sistem menggunakan kerangka kerja Laravel. Hasil penelitian ini adalah sistem monitoring aplikasi berbasis website. Sistem yang berhasil dibangun, kemudian melalui proses pengujian sistem. Pengujian unit dilakukan dengan white box testing yang menghasilkan status uji valid berdasarkan pada semua path. Pengujian validasi dengan black box testing menunjukan bahwa semua fitur valid. User Acceptance Testing menghasilkan nilai akhir 94,67% sehingga sudah sesuai dengan kebutuhan pengguna. Kontribusi sistem terhadap organisasi dapat memperbaiki efisiensi pada monitoring aplikasi dan meningkatkan efektivitas, karena data tersimpan di dalam database. Abstract Assisting the President in managing government activities pertaining to public works and public housing is the responsibility of the Ministry of Public Works and Public Housing in Indonesia. The Ministry of PUPR owns a considerable amount of software, so it requires monitoring application data collection. In monitoring applications at the PUPR ministry, they still use Google Workspace. This process causes them to have to check each application, which becomes inefficient. Thus, it requires a solution through the development of an application monitoring system. Monitoring activities that can be carried out on this system can track the status of application and manage software data. This application is designed using the Rational Unified Process (RUP) method. The approach is carried out using object-oriented development with UML. The system implementation process uses the Laravel framework. The result of this research is a website-based application monitoring system. The system that is successfully built then goes through the system testing process. Unit testing is done by white box testing, which produces a valid test status based on all paths. Validation testing with black box testing shows that all features are valid. User Acceptance Testing produces a final value of 94.67% so that it is in accordance with user needs. The contribution of the system to the organization can improve efficiency in application monitoring and increase effectiveness be","PeriodicalId":32501,"journal":{"name":"Jurnal Teknologi Informasi dan Ilmu Komputer","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136077325","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Analisis Dampak Kabut Asap dari Kebakaran Hutan dan Lahan dengan Pendekatan Text Mining","authors":"Zuliar Efendi, Imas Sukaesih Sitanggang, Lailan Syaufina","doi":"10.25126/jtiik.20231057248","DOIUrl":"https://doi.org/10.25126/jtiik.20231057248","url":null,"abstract":"Kebakaran hutan dan lahan (karhutla) berdampak buruk bagi lingkungan serta ekosistem. Kabut asap merupakan salah satu akibat yang ditimbulkan dari kebakaran hutan dan lahan. Keresahan dari munculnya kabut asap dan kebakaran hutan menjadi trending topic pada media sosial Twitter. Analisis Twitter perlu dilakukan untuk melihat kesesuaian hashtag yang digunakan dengan topik yang dibahas yaitu kabut asap. Data Twitter dapat dianalisis menggunakan text mining. Penelitian ini bertujuan untuk melihat hubungan antara percakapan di media sosial Twitter dengan kejadian kabut asap yang muncul dari kebakaran hutan dan lahan. Metode yang digunakan adalah teknik text mining yaitu menggunakan algoritme clustering. Data yang digunakan adalah data tweet terkait kabut asap di Provinsi Riau pada jarak 11 – 17 September 2019 dan juga data hotspot atau titik panas serta citra Sentinel2. Data tweet dikelompokkan dengan beberapa percobaan pada jarak antar cluster yaitu single linkage, complete linkage, average linkage, dan ward. Hasil clustering menunjukkan bahwa validitas cluster tertinggi memiliki silhouette index sebesar, 0,3360 dengan jarak antar cluster menggunakan ward. Hasil cluster menunjukkan bahwa terdapat tiga cluster yang dominan pembahasannya terkait kabut asap. Data Twitter pada ketiga cluster tersebut memiliki ciri istilah atau term yang berkaitan dengan kabut asap antara lain \"kabut\", \"asap\", dan \"udara\". terdapat di wilayah Pekanbaru serta wilayah Bengkalis, Provinsi Riau. Hasil dapat menjadi salah satu cara pengendalian karhutla yaitu deteksi dini dengan menggunakan media sosial Twitter. Abstract Forest and land fires have a harmful impact on the environment and ecosystem. Haze is one of the consequences that arise from forest fires and the environment. Anxiety about haze and forest fires is a trending topic on social media Twitter. Twitter analysis needs to be done to see the compatibility of the hashtags used with the haze topic. The Twitter data can be analyzed using text mining. This study aims to see the relation between conversations on social media Twitter and the occurrence of haze that arises from forest and land fires. The method used is a text mining technique that uses a clustering algorithm. The data used are tweet data related to haze in Riau Province in the range 11-17 September 2019 as well as hotspot data and Sentinel-2 imagery. Tweet data were clustered by several experiments on the distance between clusters, namely single linkage, complete linkage, average linkage, and ward. Clustering results show that the highest cluster validity has a silhouette index of 0.3360 with the distance between clusters using wards. The cluster results show that there are three clusters that are dominant in the discussion related to haze. The Twitter data for the three clusters has the characteristics of terms related to smog, including \"kabut\", \"asap\", and \"udara\". The impact felt by the people of Riau Province through social media Twitter related to th","PeriodicalId":32501,"journal":{"name":"Jurnal Teknologi Informasi dan Ilmu Komputer","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136077632","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Optimalisasi Proses Klasifikasi Dengan Menambahkan Semantik Pada Kebutuhan Non-Fungsional Berbasis ISO/IEC 25010","authors":"Lukman Hakim, Choirul Huda","doi":"10.25126/jtiik.20231057081","DOIUrl":"https://doi.org/10.25126/jtiik.20231057081","url":null,"abstract":"Kebutuhan non-fungsional (NFRs) memiliki peranan yang sangat penting untuk merancang sebuah sistem. Tetapi, mengidentifikasi NFRs masih menjadi tantangan nyata. NFRs dapat digunakan untuk memastikan apakah sistem sesuai dengan kebutuhan pengguna. Oleh karena itu, dibutuhkan suatu sistem untuk dapat mengidentifikasi NFRs. Penelitian sebelumnya menggunakan dataset dengan jumlah NFRs lebih banyak dibanding kebutuhan fungsional (FRs) memperoleh nilai tinggi. Akan tetapi, faktanya adalah NFRs lebih sedikit dari pada FRs. Penelitian selanjutnya menggunakan dataset dengan jumlah NFRs lebih sedikit dibandingkan (FRs) memperoleh nilai rendah terutama precision dan recall. Berdasarkan permasalahan pada penelitian sebelumnya, perlu dilakukan optimalisasi dengan cara menambahkan semantik pada metode FSKNN. Sistem yang digunakan untuk mengidentifikasi NFRs terdiri dari dua tahap. Pertama, sistem akan menghasilkan data latih secara otomatis tanpa pengukuran semantik. Setelah itu, data latih tersebut ditambahkan pengukuran semantik dan menghasilkan data latih baru. Kedua, proses klasifikasi menggunakan FSKNN. Pengujian dilakukan berdasarkan nilai ketetanggaan tertinggi. Hasil dari pengujian menggunakan dataset dengan penambahan pengukuran semantik memperoleh nilai accuracy, precision, dan recall lebih baik yaitu sebesar 98,04%, 25,05%, dan 21,35. Data latih baru dengan penambahan semantik memperoleh hasil lebih tinggi dari data latih tanpa penambahan semantik. Nilai precision rendah karena dataset yang digunakan tidak seimbang. Abstract Non-functional requirements (NFRs) are very important to design a system. However, identifying NFRs remains a real challenge. NFRs can be used to determine whether the system meets user requirements. Therefore, we need a system to be able to identify NFRs. Previous studies using a dataset with a higher number of NFRs than functional requirements (FRs) obtained high scores. However, the fact is that there are fewer NFRs than FRs. Subsequent studies using datasets with fewer NFRs than FRs obtain low values, especially precision, and recall. Based on the problems in previous studies, it is necessary to optimize by adding semantics to the FSKNN method. The system used to identify NFRs consists of two stages. First, the system will generate training data automatically without semantic measurements. After that, the training data is added with semantic measurements and generates new training data. Second, the classification process uses FSKNN. Testing is done based on the highest neighbor value. The results of testing using a dataset with the addition of semantic measurements obtained better accuracy, precision, and recall values of 98,04%, 25,05%, and 21,35. New training data with semantic additions obtains higher results than training data without semantic additions. The precision value is low because the dataset used is unbalanced.","PeriodicalId":32501,"journal":{"name":"Jurnal Teknologi Informasi dan Ilmu Komputer","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136077986","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Penerapan Metode Simple Additive Weighting dalam Pemeringkatan Kinerja Keuangan Perusahaan Sektor Teknologi yang Terdaftar di Bei","authors":"I Made Satya Sundara, I Gst. Agung Pramesti Dwi Putri, I Nyoman Yudi Anggara Wijaya","doi":"10.25126/jtiik.20231057329","DOIUrl":"https://doi.org/10.25126/jtiik.20231057329","url":null,"abstract":"Investasi merupakan penempatan sejumlah dana pada saat ini dengan tujuan mendapatkan keuntungan atau laba di masa yang akan datang. Berdasarkan laporan Kustodian Sentral Efek Indonesia (KSEI), dari tahun 2019 sampai tahun 2022 jumlah investor pasar modal selalu mengalami peningkatan. Meskipun mengalami peningkatan pada jumlah investor pasar modal, namun tingkat literasi keuangan masyarakat Indonesia pada tahun 2022 hanya sebesar 49,68 persen, dapat dikatakan bahwa pemahaman seseorang terhadap isu-isu keuangan masih tergolong rendah. Rendahnya tingkat literasi keuangan seseorang dapat menyebabkan risiko salah berinvestasi sehingga mengakibatkan kerugian di masa depan. Untuk itu, penelitian ini bertujuan untuk membantu calon investor dalam pengambilan keputusan memilih perusahaan dengan kinerja keuangan terbaik pada sektor teknologi menggunakan metode SAW (Simple Additive Weighting). Metode SAW digunakan dalam menghasilkan ranking perusahaan teknologi sebagai acuan calon investor untuk berinvestasi. Kriteria yang digunakan untuk mengukur kinerja keuangan perusahaan teknologi adalah 4 rasio keuangan yaitu rasio lancar, rasio kas, rasio utang terhadap ekuitas dan margin laba kotor. Jumlah alternatif yang digunakan pada penelitian ini berjumlah 8 alternatif. Hasil penelitian ini adalah perusahaan MLPT sebagai perusahaan dengan kinerja keuangan terbaik dalam sektor teknologi dengan nilai tertinggi yaitu 0.866. Dari hasil perhitungan metode SAW tersebut, maka sangat direkomendasikan untuk memilih perusahaan MLPT sebagai acuan untuk berinvestasi bagi calon investor. Abstract Investment is the placement of a certain amount of funds at present with the aim of gaining profit or returns in the future. According to the report from the Indonesia Central Securities Depository (KSEI), from 2019 to 2022, the number of investors in the capital market has consistently increased. However, despite this growth in the number of investors in the capital market, the level of financial literacy among the Indonesian population in 2022 is only 49.68%, indicating that the understanding of financial issues among individuals is still relatively low. The low level of financial literacy can lead to the risk of making incorrect investment decisions, resulting in potential losses in the future. Therefore, this research aims to assist prospective investors in making decisions in selecting companies with the best financial performance in the technology sector using the Simple Additive Weighting (SAW) method. The SAW method is employed to generate a ranking of technology companies that serve as a reference for prospective investors in making investment decisions. The criteria used to measure the financial performance of technology companies include four financial ratios: current ratio, cash ratio, debt-to-equity ratio, and gross profit margin. There are a total of 8 alternatives considered in this research. The result of this study indicates that MLPT company performs the best in ter","PeriodicalId":32501,"journal":{"name":"Jurnal Teknologi Informasi dan Ilmu Komputer","volume":"74 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136077464","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Deep Learning Image Classification Rontgen Dada pada Kasus Covid-19 Menggunakan Algoritma Convolutional Neural Network","authors":"Leni Anggraini Susanti, Agus Mohamad Soleh, Bagus Sartono","doi":"10.25126/jtiik.20231057142","DOIUrl":"https://doi.org/10.25126/jtiik.20231057142","url":null,"abstract":"Penelitian ini mengusulkan penggunaan Convolutional Neural Network (CNN) dengan arsitektur VGGNet-19 dan ResNet-50 untuk diagnosis COVID-19 melalui analisis citra rontgen dada. Modifikasi dilakukan dengan membandingkan nilai regularisasi dropout 50% dan 80% untuk kedua arsitektur dan mengubah jumlah lapisan klasfikasi menjadi 4 kelas. Selanjutnya, kinerja model dibandingkan berdasarkan ukuran dataset. Dataset terdiri dari 21165 citra, dengan pembagian 10% sebagai data uji dan 90% data dibagi menjadi data latih (80%) dan data validasi (20%). Kinerja model dievaluasi menggunakan metode validasi silang berulang 5 kali lipat. Proses pelatihan menggunakan learning rate 0.0001, optimasi stochastic gradient descent (SGD), dan sepuluh iterasi. Hasil penelitian menunjukkan bahwa penambahan lapisan dropout dengan peluang 50% untuk kedua arsitektur secara efektif mengatasi overfitting dan meningkatkan performa model. Ditemukan bahwa kinerja yang lebih baik dicapai pada ukuran kumpulan data lebih besar dan memberikan peningkatan signifikan pada kinerja model. Hasil klasifikasi menunjukkan arsitektur ResNet-50 mencapai akurasi rata-rata 94.4%, recall rata-rata 94.1%, presisi rata-rata 95.5%, spesifisitas rata-rata 97% dan F1-score rata-rata 94.8%. Sedangkan arsitektur VGGNet-19 mencapai akurasi rata-rata 91%, recall rata-rata 89%, presisi rata-rata 95.0%, spesifisitas rata-rata 96.8% dan F1-score rata-rata 92.7%. Pemanfaatan model ini dapat membantu mengidentifikasi penyebab kematian pasien dan memberikan informasi yang berharga bagi pengambilan keputusan medis dan epidemiologi. Abstract This research proposes using a Convolutional Neural Network (CNN) with VGGNet-19 and ResNet-50 architectures for COVID-19 diagnosis through chest X-ray image analysis. Modifications were made by comparing the dropout regularization values of 50% and 80% for both architectures and altering the number of classification layers to 4 classes. Furthermore, the model's performance was compared based on dataset size. The dataset comprised 21,165 images, with a division of 10% for testing and 90% divided into training data (80%) and validation data (20%). The model's performance was evaluated using the 5-fold repeat cross-validation method. The training process employed a learning rate of 0.0001, stochastic gradient descent (SGD) optimization, and ten iterations. The study's results indicate that adding dropout layers with a 50% probability for both architectures effectively addressed overfitting and improved the model's performance. It was found that better performance was achieved with larger dataset sizes. The classification results indicate the ResNet-50 architecture achieved an average accuracy of 94.4%, average recall of 94.1%, average precision of 95.5%, average specificity of 97%, and average F1-score of 94.8%. Meanwhile, the VGGNet-19 architecture achieved an average accuracy of 91%, an average recall of 89%, average precision of 95.0%, average specificity of 96.8%, and an av","PeriodicalId":32501,"journal":{"name":"Jurnal Teknologi Informasi dan Ilmu Komputer","volume":"127 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136077469","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Pendekatan Bayes-HDSS dalam Menentukan Status Pantauan Gizi Balita","authors":"Riki Hisbullah, Muhammad Siddik Hasibuan","doi":"10.25126/jtiik.20231057437","DOIUrl":"https://doi.org/10.25126/jtiik.20231057437","url":null,"abstract":"Teknologi dan perkembangan komputer saat ini sangat membantu banyak kebutuhan dalam kehidupan, termasuk dalam hal menggantikan kemampuan seorang ahli dalam mengerjakan dan menentukan sebuah keputusan dalam permasalahan yang terjadi pada banyak orang. Dalam perkembangan sistem pakar dan sistem pendukung keputusan juga dapat menggantikan dan menjadi solusi dari seorang ahli pakar. Bayes digunakan untuk mendiagnosis penyakit serta AHP dan TOPSIS akan digunakan untuk melakukan perangkingan penyakit pada manusia, termasuk gizi pada anak dimana sampai saat ini masalah terbesar dunia adalah bagaimana mengatasi gizi buruk yang dialami. Dengan menggunakan Sistem Pakar dan HDSS diharap Mampu menghitung kriteria yang merupakan gejala pada anak guna menghasilkan urutan anak yang menjadi fokus pantauan dimana nilai terbesar dari output sistem memberikan kepastian bahwa anak membutuhkan fokus dalam mengatasi masalah gizi yang dialaminya. Didalam Penelitian ini, Bayes, AHP dan TOPSIS mampu menghitung nilai dengan memberikan diagnosis gejala serta menempilkan nilai persentase kebutuhan pantauan pada data sampel balita yang di peroleh dari Pusat Kesehatan Masyarakat (Puskesmas) XYZ terhadap masalah gizi balita yang ada di Pusat Kesehatan Masyarakat tersebut. Dari 5 Gejala Yang di implementasikan kedalam sistem pakar (bayes) yaitu; STUNTING, GIZI LEBIH, GIZI KURANG, KWASHIORKOR, dan MARASMUS, tidak ditemukan status STUNTING. Selanjutnya pada HDSS Menghasilkan persentase 95,49% yang mana balita ini merupakan pemilik kriteria terburuk diantara balita lainnya. Abstract Technology and the development of computers are very helpful for many people in life, including in terms of replacing the ability of an expert to do and determine a decision in problems that occur to many people. In the development of expert systems and support systems, decisions can also replace and be a solution to the scarcity of an expert. Bayes is used to diagnose disease and AHP and TOPSIS will be used to rank diseases in humans, including nutrition in children where until now the world's biggest problem is how to overcome malnutrition experienced by toddlers including stunting problems, where toddler growth is not optimal. By using an Expert System and HDSS (namely AHP and TOPSIS) it is forbidden to calculate criteria that are symptoms in children, to produce a sequence of children who are the focus of monitoring. The greatest value of the output system provides certainty that children need focus in overcoming the problem of malnutrition. Deepened by this research, Bayes, AHP and TOPSIS were able to calculate the value by providing a diagnosis of symptoms and displaying the percentage value of the need for monitoring on the toddler sample data obtained from the XYZ Community Health Center (Puskesmas) for toddler nutrition problems in the Community Health Center. Of the 5 Symptoms implemented in the expert system (bayes) namely STUNTING, OVER NUTRITION, MALNUTRITION, KWASHIORKOR, and MARASMUS, no","PeriodicalId":32501,"journal":{"name":"Jurnal Teknologi Informasi dan Ilmu Komputer","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136077471","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Seleksi Fitur dengan Particle Swarm Optimization pada Klasifikasi Penyakit Parkinson Menggunakan XGBoost","authors":"Deni Kurnia, Muhammad Itqan Mazdadi, Dwi Kartini, Radityo Adi Nugroho, Friska Abadi","doi":"10.25126/jtiik.20231057252","DOIUrl":"https://doi.org/10.25126/jtiik.20231057252","url":null,"abstract":"Penyakit Parkinson merupakan gangguan pada sistem saraf pusat yang mempengaruhi sistem motorik. Diagnosis penyakit ini cukup sulit dilakukan karena gejalanya yang serupa dengan penyakit lain. Saat ini diagnosa dapat dilakukan menggunakan machine learning dengan memanfaatkan rekaman suara pasien. Fitur yang dihasilkan dari ekstraksi rekaman suara tersebut relatif cukup banyak sehingga seleksi fitur perlu dilakukan untuk menghindari memburuknya kinerja sebuah model. Pada penelitian ini, Particle Swarm Optimization digunakan sebagai seleksi fitur, sedangkan XGBoost akan digunakan sebagai model klasifikasi. Selain itu model juga akan diterapkan SMOTE untuk mengatasi masalah ketidakseimbangan kelas data dan hyperparameter tuning pada XGBoost untuk mendapatkan hyperparameter yang optimal. Hasil pengujian menunjukkan bahwa nilai AUC pada model dengan seleksi fitur tanpa SMOTE dan hyperparameter tuning adalah 0,9325, sedangkan pada model tanpa seleksi fitur hanya mendapat nilai AUC sebesar 0,9250. Namun, ketika kedua teknik SMOTE dan hyperparameter tuning digunakan bersamaan, penggunaan seleksi fitur mampu memberikan peningkatan kinerja pada model. Model dengan seleksi fitur mendapat nilai AUC sebesar 0,9483, sedangkan model tanpa seleksi fitur hanya mendapat nilai AUC sebesar 0,9366. Abstract Parkinson's disease is a disorder of the central nervous system that affects the motor system. Diagnosis of this disease is quite difficult because the symptoms are similar to other diseases. Currently, diagnosis can be done using machine learning by utilizing patient voice recordings. The features generated from the extraction of voice recordings are relatively large, so feature selection needs to be done to avoid deteriorating the performance of a model. In this research, Particle Swarm Optimization is used as feature selection, while XGBoost will be used as a classification model. In addition, the model will also be applied SMOTE to overcome the problem of data class imbalance and hyperparameter tuning on XGBoost to get optimal hyperparameters. The test results show that the AUC value on the model with feature selection without SMOTE and hyperparameter tuning is 0.9325, while the model without feature selection only gets an AUC value of 0.9250. However, when both SMOTE and hyperparameter tuning techniques are used together, the use of feature selection is able to provide improved performance on the model. The model with feature selection gets an AUC value of 0.9483, while the model without feature selection only gets an AUC value of 0.9366.","PeriodicalId":32501,"journal":{"name":"Jurnal Teknologi Informasi dan Ilmu Komputer","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136077472","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}